Commit Graph

53 Commits (398f42de5fd9f32a8a8977cd88b88b1890763e9a)

Author SHA1 Message Date
Filip Petkovski 583f3e587c
Optimize histogram iterators (#13340)
Optimize histogram iterators

Histogram iterators allocate new objects in the AtHistogram and
AtFloatHistogram methods, which makes calculating rates over long
ranges expensive.

In #13215 we allowed an existing object to be reused
when converting an integer histogram to a float histogram. This commit follows
the same idea and allows injecting an existing object in the AtHistogram and
AtFloatHistogram methods. When the injected value is nil, iterators allocate
new histograms, otherwise they populate and return the injected object.

The commit also adds a CopyTo method to Histogram and FloatHistogram which
is used in the BufferedIterator to overwrite items in the ring instead of making
new copies.

Note that a specialized HPoint pool is needed for all of this to work 
(`matrixSelectorHPool`).

---------

Signed-off-by: Filip Petkovski <filip.petkovsky@gmail.com>
Co-authored-by: George Krajcsovits <krajorama@users.noreply.github.com>
2024-01-23 17:02:14 +01:00
Marc Tuduri af7c31ee10
PR feedback
Signed-off-by: Marc Tuduri <marctc@protonmail.com>
2023-10-18 11:53:50 +02:00
Marc Tuduri 8fededf6ad
promql(histograms): Change sample total calculation for histograms
Signed-off-by: Marc Tuduri <marctc@protonmail.com>
2023-10-18 11:51:11 +02:00
zenador 69edd8709b
Add warnings (and annotations) to PromQL query results (#12152)
Return annotations (warnings and infos) from PromQL queries

This generalizes the warnings we have already used before (but only for problems with remote read) as "annotations".

Annotations can be warnings or infos (the latter could be false positives). We do not treat them different in the API for now and return them all as "warnings". It would be easy to distinguish them and return infos separately, should that appear useful in the future.

The new annotations are then used to create a lot of warnings or infos during PromQL evaluations. Partially these are things we have wanted for a long time (e.g. inform the user that they have applied `rate` to a metric that doesn't look like a counter), but the new native histograms have created even more needs for those annotations (e.g. if a query tries to aggregate float numbers with histograms).

The annotations added here are not yet complete. A prominent example would be a warning about a range too short for a rate calculation. But such a warnings is more tricky to create with good fidelity and we will tackle it later.

Another TODO is to take annotations into account when evaluating recording rules.

---------

Signed-off-by: Jeanette Tan <jeanette.tan@grafana.com>
2023-09-14 18:57:31 +02:00
cui fliter 096ceca44f
remove repetitive words (#12556)
Signed-off-by: cui fliter <imcusg@gmail.com>
2023-07-13 15:53:40 +02:00
beorn7 c0879d64cf promql: Separate `Point` into `FPoint` and `HPoint`
In other words: Instead of having a “polymorphous” `Point` that can
either contain a float value or a histogram value, use an `FPoint` for
floats and an `HPoint` for histograms.

This seemingly small change has a _lot_ of repercussions throughout
the codebase.

The idea here is to avoid the increase in size of `Point` arrays that
happened after native histograms had been added.

The higher-level data structures (`Sample`, `Series`, etc.) are still
“polymorphous”. The same idea could be applied to them, but at each
step the trade-offs needed to be evaluated.

The idea with this change is to do the minimum necessary to get back
to pre-histogram performance for functions that do not touch
histograms. Here are comparisons for the `changes` function. The test
data doesn't include histograms yet. Ideally, there would be no change
in the benchmark result at all.

First runtime v2.39 compared to directly prior to this commit:

```
name                                                  old time/op    new time/op    delta
RangeQuery/expr=changes(a_one[1d]),steps=1-16            391µs ± 2%     542µs ± 1%  +38.58%  (p=0.000 n=9+8)
RangeQuery/expr=changes(a_one[1d]),steps=10-16           452µs ± 2%     617µs ± 2%  +36.48%  (p=0.000 n=10+10)
RangeQuery/expr=changes(a_one[1d]),steps=100-16         1.12ms ± 1%    1.36ms ± 2%  +21.58%  (p=0.000 n=8+10)
RangeQuery/expr=changes(a_one[1d]),steps=1000-16        7.83ms ± 1%    8.94ms ± 1%  +14.21%  (p=0.000 n=10+10)
RangeQuery/expr=changes(a_ten[1d]),steps=1-16           2.98ms ± 0%    3.30ms ± 1%  +10.67%  (p=0.000 n=9+10)
RangeQuery/expr=changes(a_ten[1d]),steps=10-16          3.66ms ± 1%    4.10ms ± 1%  +11.82%  (p=0.000 n=10+10)
RangeQuery/expr=changes(a_ten[1d]),steps=100-16         10.5ms ± 0%    11.8ms ± 1%  +12.50%  (p=0.000 n=8+10)
RangeQuery/expr=changes(a_ten[1d]),steps=1000-16        77.6ms ± 1%    87.4ms ± 1%  +12.63%  (p=0.000 n=9+9)
RangeQuery/expr=changes(a_hundred[1d]),steps=1-16       30.4ms ± 2%    32.8ms ± 1%   +8.01%  (p=0.000 n=10+10)
RangeQuery/expr=changes(a_hundred[1d]),steps=10-16      37.1ms ± 2%    40.6ms ± 2%   +9.64%  (p=0.000 n=10+10)
RangeQuery/expr=changes(a_hundred[1d]),steps=100-16      105ms ± 1%     117ms ± 1%  +11.69%  (p=0.000 n=10+10)
RangeQuery/expr=changes(a_hundred[1d]),steps=1000-16     783ms ± 3%     876ms ± 1%  +11.83%  (p=0.000 n=9+10)
```

And then runtime v2.39 compared to after this commit:

```
name                                                  old time/op    new time/op    delta
RangeQuery/expr=changes(a_one[1d]),steps=1-16            391µs ± 2%     547µs ± 1%  +39.84%  (p=0.000 n=9+8)
RangeQuery/expr=changes(a_one[1d]),steps=10-16           452µs ± 2%     616µs ± 2%  +36.15%  (p=0.000 n=10+10)
RangeQuery/expr=changes(a_one[1d]),steps=100-16         1.12ms ± 1%    1.26ms ± 1%  +12.20%  (p=0.000 n=8+10)
RangeQuery/expr=changes(a_one[1d]),steps=1000-16        7.83ms ± 1%    7.95ms ± 1%   +1.59%  (p=0.000 n=10+8)
RangeQuery/expr=changes(a_ten[1d]),steps=1-16           2.98ms ± 0%    3.38ms ± 2%  +13.49%  (p=0.000 n=9+10)
RangeQuery/expr=changes(a_ten[1d]),steps=10-16          3.66ms ± 1%    4.02ms ± 1%   +9.80%  (p=0.000 n=10+9)
RangeQuery/expr=changes(a_ten[1d]),steps=100-16         10.5ms ± 0%    10.8ms ± 1%   +3.08%  (p=0.000 n=8+10)
RangeQuery/expr=changes(a_ten[1d]),steps=1000-16        77.6ms ± 1%    78.1ms ± 1%   +0.58%  (p=0.035 n=9+10)
RangeQuery/expr=changes(a_hundred[1d]),steps=1-16       30.4ms ± 2%    33.5ms ± 4%  +10.18%  (p=0.000 n=10+10)
RangeQuery/expr=changes(a_hundred[1d]),steps=10-16      37.1ms ± 2%    40.0ms ± 1%   +7.98%  (p=0.000 n=10+10)
RangeQuery/expr=changes(a_hundred[1d]),steps=100-16      105ms ± 1%     107ms ± 1%   +1.92%  (p=0.000 n=10+10)
RangeQuery/expr=changes(a_hundred[1d]),steps=1000-16     783ms ± 3%     775ms ± 1%   -1.02%  (p=0.019 n=9+9)
```

In summary, the runtime doesn't really improve with this change for
queries with just a few steps. For queries with many steps, this
commit essentially reinstates the old performance. This is good
because the many-step queries are the one that matter most (longest
absolute runtime).

In terms of allocations, though, this commit doesn't make a dent at
all (numbers not shown). The reason is that most of the allocations
happen in the sampleRingIterator (in the storage package), which has
to be addressed in a separate commit.

Signed-off-by: beorn7 <beorn@grafana.com>
2023-04-13 19:25:16 +02:00
tyltr 24a9678dcc
typo 'efficcient' (#12090)
Signed-off-by: tylitianrui <tylitianrui@126.com>
2023-03-08 09:59:08 +00:00
Bryan Boreham 463f5cafdd storage: re-use iterators to save garbage
Re-use previous memory if it is already of the correct type.

In `NewListSeries` we hoist the conversion to an interface value out
so it only allocates once.

Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
2022-12-15 18:32:45 +00:00
Bryan Boreham 3c7de69059 storage: allow re-use of iterators
Patterned after `Chunk.Iterator()`: pass the old iterator in so it
can be re-used to avoid allocating a new object.

(This commit does not do any re-use; it is just changing all the method
signatures so re-use is possible in later commits.)

Signed-off-by: Bryan Boreham <bjboreham@gmail.com>
2022-12-15 18:32:45 +00:00
beorn7 53982c3562 Merge branch 'main' into sparsehistogram 2022-07-13 21:27:20 +02:00
Oleg Zaytsev d2abe9a58a
Shortcut `ContainsSameLabelset()` (#11000)
* Shortcut Matrix.ContainsSameLabelset()

It's quite often to execute this check on a Matrix that has zero or only
one series. There's no need to allocate a map for those cases.

There's also a one-liner for two-series case, so why not using it?

Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>

* Add license header

Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>

* Optimize Vector.ContainsSameLabelset

Signed-off-by: Oleg Zaytsev <mail@olegzaytsev.com>
2022-07-13 15:18:10 +05:30
beorn7 40ad5e284a Merge branch 'main' into beorn7/sparsehistogram 2022-06-09 20:50:30 +02:00
Matthieu MOREL 0906f2eafa
refactor (promql): move from github.com/pkg/errors to 'errors' and 'fmt' (#10817)
Signed-off-by: Matthieu MOREL <mmorel-35@users.noreply.github.com>

Co-authored-by: Matthieu MOREL <mmorel-35@users.noreply.github.com>
2022-06-08 10:47:52 +02:00
beorn7 d16b314b72 Histogram: Do not render empty buckets in JSON output
While empty buckets can make sense in the internal representation (by
joining spans that would otherwise need more overhead for separate
representation), there are no spans in the JSON rendering. Therefore,
the JSON should not contain any empty buckets, since any buckets not
included in the output counts as empty anyway.

This changes both the inefficient MarshalJSON implementation as well
as the jsoniter implementation.

Signed-off-by: beorn7 <beorn@grafana.com>
2022-05-03 18:18:55 +02:00
beorn7 37bbc07118 Histogram: Add jsoniter marshaling
This now even enables jsoniter marshaling of Points in an instant
query (which previously used the traditional JSON marshaling).

Signed-off-by: beorn7 <beorn@grafana.com>
2022-04-26 15:19:59 +02:00
beorn7 99894f6afa Histogram: Implement inefficient JSON rendering
Format is according to example 4 in
https://docs.google.com/document/d/1Efu0LX-fgNWix6ehfeCR0FzeWtHvftWFNoy7cYW9nqU/edit#

This is inefficient as it doesn't use jsoniter. It actually prevents
it for regular Points (with a conventional float Value), too.

Signed-off-by: beorn7 <beorn@grafana.com>
2022-04-14 20:38:49 +02:00
beorn7 e4e24453fa Merge branch 'main' into beorn7/merge2 2021-11-30 17:19:06 +01:00
Björn Rabenstein 7e42acd3b1
tsdb: Rework iterators (#9877)
- Pick At... method via return value of Next/Seek.
- Do not clobber returned buckets.
- Add partial FloatHistogram suppert.

Note that the promql package is now _only_ dealing with
FloatHistograms, following the idea that PromQL only knows float
values.

As a byproduct, I have removed the histogramSeries metric. In my
understanding, series can have both float and histogram samples, so
that metric doesn't make sense anymore.

As another byproduct, I have converged the sampleBuf and the
histogramSampleBuf in memSeries into one. The sample type stored in
the sampleBuf has been extended to also contain histograms even before
this commit.

Signed-off-by: beorn7 <beorn@grafana.com>
2021-11-29 13:24:23 +05:30
beorn7 9672ade191 Promql: Add clarifying note to Point.MarshalJSON
Signed-off-by: beorn7 <beorn@grafana.com>
2021-11-25 13:32:37 +01:00
Ganesh Vernekar 2a3d62ac84
Revert "promql: Remove unused Point.MarshalJSON method (#9860)" (#9864)
This reverts commit 427425cc9f.

Signed-off-by: Ganesh Vernekar <ganeshvern@gmail.com>
2021-11-25 17:07:55 +05:30
Björn Rabenstein 427425cc9f
promql: Remove unused Point.MarshalJSON method (#9860)
JSON marshaling is only needed for the HTTP API. Since Point is such a
frequently marshaled type, it gets an optimized treatment directly in
web/api/v1/api.go. The MarshalJSON method still provided in the promql
package is therefore unused and its existence is confusing.

Signed-off-by: beorn7 <beorn@grafana.com>
2021-11-25 12:38:24 +05:30
beorn7 5d4db805ac Merge branch 'main' into sparsehistogram 2021-11-17 19:57:31 +01:00
beorn7 9b30ca2598 promql: Support histogram in value string representation
Signed-off-by: beorn7 <beorn@grafana.com>
2021-11-15 20:36:44 +01:00
beorn7 4c28d9fac7 Move to histogram.Histogram pointers
This is to avoid copying the many fields of a histogram.Histogram all
the time.

This also fixes a bunch of formerly broken tests.

Signed-off-by: beorn7 <beorn@grafana.com>
2021-11-12 23:17:35 +01:00
beorn7 c954cd9d1d Move packages out of deprecated pkg directory
This creates a new `model` directory and moves all data-model related
packages over there:
  exemplar labels relabel rulefmt textparse timestamp value

All the others are more or less utilities and have been moved to `util`:
  gate logging modetimevfs pool runtime

Signed-off-by: beorn7 <beorn@grafana.com>
2021-11-09 08:03:10 +01:00
beorn7 8f92c90897 Add TODOs and some minor tweaks
Signed-off-by: beorn7 <beorn@grafana.com>
2021-11-07 17:12:04 +01:00
Ganesh Vernekar c8b267efd6
Get histograms from TSDB to the rate() function implementation
Signed-off-by: Ganesh Vernekar <ganeshvern@gmail.com>
2021-11-03 19:04:18 +05:30
beorn7 7a8bb8222c Style cleanup of all the changes in sparsehistogram so far
A lot of this code was hacked together, literally during a
hackathon. This commit intends not to change the code substantially,
but just make the code obey the usual style practices.

A (possibly incomplete) list of areas:

* Generally address linter warnings.

* The `pgk` directory is deprecated as per dev-summit. No new packages should
  be added to it. I moved the new `pkg/histogram` package to `model`
  anticipating what's proposed in #9478.

* Make the naming of the Sparse Histogram more consistent. Including
  abbreviations, there were just too many names for it: SparseHistogram,
  Histogram, Histo, hist, his, shs, h. The idea is to call it "Histogram" in
  general. Only add "Sparse" if it is needed to avoid confusion with
  conventional Histograms (which is rare because the TSDB really has no notion
  of conventional Histograms). Use abbreviations only in local scope, and then
  really abbreviate (not just removing three out of seven letters like in
  "Histo"). This is in the spirit of
  https://github.com/golang/go/wiki/CodeReviewComments#variable-names

* Several other minor name changes.

* A lot of formatting of doc comments. For one, following
  https://github.com/golang/go/wiki/CodeReviewComments#comment-sentences
  , but also layout question, anticipating how things will look like
  when rendered by `godoc` (even where `godoc` doesn't render them
  right now because they are for unexported types or not a doc comment
  at all but just a normal code comment - consistency is queen!).

* Re-enabled `TestQueryLog` and `TestEndopints` (they pass now,
  leaving them disabled was presumably an oversight).

* Bucket iterator for histogram.Histogram is now created with a
  method.

* HistogramChunk.iterator now allows iterator recycling. (I think
  @dieterbe only commented it out because he was confused by the
  question in the comment.)

* HistogramAppender.Append panics now because we decided to treat
  staleness marker differently.

Signed-off-by: beorn7 <beorn@grafana.com>
2021-10-11 13:02:03 +02:00
Ganesh Vernekar 8b70e87ab9
Merge remote-tracking branch 'upstream/main' into sparse-refactor
Signed-off-by: Ganesh Vernekar <ganeshvern@gmail.com>
2021-08-05 12:16:08 +05:30
Darshan Chaudhary c4f2e9eec5
Add present_over_time (#9097)
* Add present_over_time

Signed-off-by: darshanime <deathbullet@gmail.com>

* Add tests for present_over_time

Signed-off-by: darshanime <deathbullet@gmail.com>

* Address PR comments

Signed-off-by: darshanime <deathbullet@gmail.com>

* Add documentation for present_over_time

Signed-off-by: darshanime <deathbullet@gmail.com>

* Update documentation

Signed-off-by: darshanime <deathbullet@gmail.com>

* Update documentation comment

Signed-off-by: darshanime <deathbullet@gmail.com>
2021-07-29 12:38:11 +02:00
Ganesh Vernekar f4d3af73f0
Query histograms from TSDB and unit test for append+query (#9022)
Signed-off-by: Ganesh Vernekar <ganeshvern@gmail.com>
2021-06-30 20:18:13 +05:30
Ganesh Vernekar 04ad56d9b8
Append sparse histograms into the Head block (#9013)
* Append sparse histograms into the Head block

Signed-off-by: Ganesh Vernekar <ganeshvern@gmail.com>

* Add AtHistogram() to Iterator interface. Make HistoChunk conform to Chunk interface.

Signed-off-by: Ganesh Vernekar <ganeshvern@gmail.com>
2021-06-29 20:08:46 +05:30
Julien Pivotto 4e5b1722b3
Move away from testutil, refactor imports (#8087)
Signed-off-by: Julien Pivotto <roidelapluie@inuits.eu>
2020-10-22 11:00:08 +02:00
Tobias Guggenmos 4835bbf376
Merge branch 'master' into split_parser 2020-02-19 15:18:13 +01:00
Bartlomiej Plotka 34426766d8 Unify Iterator interfaces. All point to storage now.
This is part of https://github.com/prometheus/prometheus/pull/5882 that can be done to simplify things.
All todos I added will be fixed in follow up PRs.

* querier.Querier, querier.Appender, querier.SeriesSet, and querier.Series interfaces merged
with storage interface.go. All imports that.
* querier.SeriesIterator replaced by chunkenc.Iterator
* Added chunkenc.Iterator.Seek method and tests for xor implementation (?)
* Since we properly handle SelectParams for Select methods I adjusted min max
based on that. This should help in terms of performance for queries with functions like offset.
* added Seek to deletedIterator and test.
* storage/tsdb was removed as it was only a unnecessary glue with incompatible structs.

No logic was changed, only different source of abstractions, so no need for benchmarks.

Signed-off-by: Bartlomiej Plotka <bwplotka@gmail.com>
2020-02-17 18:03:54 +00:00
Tobias Guggenmos 2d77611f73 Unbump year number
Signed-off-by: Tobias Guggenmos <tguggenm@redhat.com>
2020-02-17 16:09:23 +01:00
Tobias Guggenmos 43d206f0a1 Add missing file
Signed-off-by: Tobias Guggenmos <tguggenm@redhat.com>
2020-02-17 16:09:23 +01:00
Tobias Guggenmos fab2373752 Add everything the parser needs to build
Signed-off-by: Tobias Guggenmos <tguggenm@redhat.com>
2020-02-17 16:05:21 +01:00
Julien Pivotto f315c69129 promql: fix typo in value.go (#6491)
Signed-off-by: Julien Pivotto <roidelapluie@inuits.eu>
2019-12-19 22:30:32 +00:00
AllenZMC 8d6ec5acdc fix word 'seriess' to 'series' (#5828)
Signed-off-by: czm <zhongming.chang@daocloud.io>
2019-08-04 16:52:51 +01:00
Tariq Ibrahim 8fdfa8abea refine error handling in prometheus (#5388)
i) Uses the more idiomatic Wrap and Wrapf methods for creating nested errors.
ii) Fixes some incorrect usages of fmt.Errorf where the error messages don't have any formatting directives.
iii) Does away with the use of fmt package for errors in favour of pkg/errors

Signed-off-by: tariqibrahim <tariq181290@gmail.com>
2019-03-26 00:01:12 +01:00
Simon Pasquier f678e27eb6
*: use latest release of staticcheck (#5057)
* *: use latest release of staticcheck

It also fixes a couple of things in the code flagged by the additional
checks.

Signed-off-by: Simon Pasquier <spasquie@redhat.com>

* Use official release of staticcheck

Also run 'go list' before staticcheck to avoid failures when downloading packages.

Signed-off-by: Simon Pasquier <spasquie@redhat.com>
2019-01-04 14:47:38 +01:00
Ganesh Vernekar dbe55c1352 Subquery (#4831)
Signed-off-by: Ganesh Vernekar <cs15btech11018@iith.ac.in>
2018-12-22 13:47:13 +00:00
mknapphrt f0e9196dca Return warnings on a remote read fail (#4832)
Signed-off-by: Mark Knapp <mknapp@hudson-trading.com>
2018-11-30 14:27:12 +00:00
Ben Kochie c6399296dc
Fix spelling/typos (#4921)
* Fix spelling/typos

Fix spelling/typos reported by codespell/misspell.
* UK -> US spelling changes.

Signed-off-by: Ben Kochie <superq@gmail.com>
2018-11-27 17:44:29 +01:00
Kangseok Thomas Lee bec1a2f038 Reordering fields of String datetype (#4751)
Other types has timestamp as first field, but only String type has value as first field.

Signed-off-by: gangseok.lee <gangseok.lee@samsung.com>
2018-10-17 08:52:23 +01:00
Vandewilly 1098ed89d8 Drop 'else' condition when 'if' ends with a return (#4743)
This commit drops the else condition when the if block ends with a
return statement.

Signed-off-by: Vandewilly Silva <vandewilly.oli.silva@hpe.com>
2018-10-15 23:51:55 +01:00
Callum Styan 9bca041285 WIP: keep track of samples per query, set a max # of samples (#4513)
* keep track of samples per query, set a max # of samples that can be in
memory at once

Signed-off-by: Callum Styan <callumstyan@gmail.com>
2018-10-02 12:59:19 +01:00
Harsh Agarwal 18a9a390b5 Add duplicate-labelset check for range/instant vectors (#4589)
Signed-off-by: Harsh Agarwal <cs15btech11019@iith.ac.in>
2018-09-18 10:46:13 +01:00
Brian Brazil 5c9a6ce747 Add license to files.
This should fix CI for dev-2.0.
2017-04-19 13:46:22 +01:00